ResearchBenchmarksMultiple Change-point Detection on Story dataset Claude 4.5 K=8Follow0.33Word Distance (WD)Voting0.29080.55540.821.0846May 5, 2026Evaluation ResultsMethodMethodLinksWord Distance (WD)Cross-Entropy (CE)VotingGenerator=Claude 4.5Generator=Claude 4.52026.050.33-2.56VCPGenerator=Claude 4.5Generator=Claude 4.52026.050.33-1.22WCPGenerator=Claude 4.5Generator=Claude 4.52026.050.330.68LLMPredGenerator=Claude 4.5Generator=Claude 4.52026.050.494.96TextTilingGenerator=Claude 4.5Generator=Claude 4.52026.050.53-3.06SenPredGenerator=Claude 4.5Generator=Claude 4.52026.051.31-24.68